X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=4e951bbedc7449d899a683b8ce6f965f3d291e5e;hb=227a1d886672767e37cc86a3432952c14eb8a143;hp=21ab8119e70fe559fbe5435fea50a443b0b1459a;hpb=cd8dd7b08fddc7c2b5f218c3fcaa5dca5f9ad945;p=public-inbox.git

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 21ab8119..4e951bbe 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -12,7 +12,7 @@ use warnings;
 use base qw(PublicInbox::Search PublicInbox::Lock);
 use PublicInbox::MIME;
 use PublicInbox::InboxWritable;
-use PublicInbox::MID qw/mid_clean id_compress mid_mime mids_for_index/;
+use PublicInbox::MID qw/mid_clean mid_mime mids_for_index/;
 use PublicInbox::MsgIter;
 use Carp qw(croak);
 use POSIX qw(strftime);
@@ -34,7 +34,7 @@ sub new {
 	ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx";
 	my $levels = qr/\A(?:full|medium|basic)\z/;
 	my $inboxdir = $ibx->{inboxdir};
-	my $version = $ibx->{version} || 1;
+	my $version = $ibx->version;
 	my $indexlevel = 'full';
 	my $altid = $ibx->{altid};
 	if ($altid) {
@@ -133,16 +133,25 @@ sub add_val ($$$) {
 	$doc->add_value($col, $num);
 }
 
-sub index_text ($$$$)
-{
-	my ($self, $field, $n, $text) = @_;
-	my $tg = $self->term_generator;
+sub term_generator ($) { # write-only
+	my ($self) = @_;
+
+	$self->{term_generator} //= do {
+		my $tg = $X->{TermGenerator}->new;
+		$tg->set_stemmer($self->stemmer);
+		$tg;
+	}
+}
+
+sub index_text ($$$$) {
+	my ($self, $text, $wdf_inc, $prefix) = @_;
+	my $tg = term_generator($self); # man Search::Xapian::TermGenerator
 
 	if ($self->{indexlevel} eq 'full') {
-		$tg->index_text($field, $n, $text);
+		$tg->index_text($text, $wdf_inc, $prefix);
 		$tg->increase_termpos;
 	} else {
-		$tg->index_text_without_positions($field, $n, $text);
+		$tg->index_text_without_positions($text, $wdf_inc, $prefix);
 	}
 }
 
@@ -153,18 +162,18 @@ sub index_users ($$) {
 	my $to = $smsg->to;
 	my $cc = $smsg->cc;
 
-	$self->index_text($from, 1, 'A'); # A - author
-	$self->index_text($to, 1, 'XTO') if $to ne '';
-	$self->index_text($cc, 1, 'XCC') if $cc ne '';
+	index_text($self, $from, 1, 'A'); # A - author
+	index_text($self, $to, 1, 'XTO') if $to ne '';
+	index_text($self, $cc, 1, 'XCC') if $cc ne '';
 }
 
 sub index_diff_inc ($$$$) {
 	my ($self, $text, $pfx, $xnq) = @_;
 	if (@$xnq) {
-		$self->index_text(join("\n", @$xnq), 1, 'XNQ');
+		index_text($self, join("\n", @$xnq), 1, 'XNQ');
 		@$xnq = ();
 	}
-	$self->index_text($text, 1, $pfx);
+	index_text($self, $text, 1, $pfx);
 }
 
 sub index_old_diff_fn {
@@ -179,7 +188,7 @@ sub index_old_diff_fn {
 		$fb = join('/', @fb);
 		if ($fa eq $fb) {
 			unless ($seen->{$fa}++) {
-				$self->index_diff_inc($fa, 'XDFN', $xnq);
+				index_diff_inc($self, $fa, 'XDFN', $xnq);
 			}
 			return 1;
 		}
@@ -190,22 +199,22 @@ sub index_old_diff_fn {
 }
 
 sub index_diff ($$$) {
-	my ($self, $lines, $doc) = @_;
+	my ($self, $txt, $doc) = @_;
 	my %seen;
 	my $in_diff;
 	my @xnq;
 	my $xnq = \@xnq;
-	foreach (@$lines) {
+	foreach (split(/\n/, $txt)) {
 		if ($in_diff && s/^ //) { # diff context
-			$self->index_diff_inc($_, 'XDFCTX', $xnq);
+			index_diff_inc($self, $_, 'XDFCTX', $xnq);
 		} elsif (/^-- $/) { # email signature begins
 			$in_diff = undef;
 		} elsif (m!^diff --git ("?a/.+) ("?b/.+)\z!) {
 			my ($fa, $fb) = ($1, $2);
 			my $fn = (split('/', git_unquote($fa), 2))[1];
-			$seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
+			$seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
 			$fn = (split('/', git_unquote($fb), 2))[1];
-			$seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
+			$seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
 			$in_diff = 1;
 		# traditional diff:
 		} elsif (m/^diff -(.+) (\S+) (\S+)$/) {
@@ -213,28 +222,28 @@ sub index_diff ($$$) {
 			push @xnq, $_;
 			# only support unified:
 			next unless $opt =~ /[uU]/;
-			$in_diff = $self->index_old_diff_fn(\%seen, $fa, $fb,
+			$in_diff = index_old_diff_fn($self, \%seen, $fa, $fb,
 							$xnq);
 		} elsif (m!^--- ("?a/.+)!) {
 			my $fn = $1;
 			$fn = (split('/', git_unquote($fn), 2))[1];
-			$seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
+			$seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
 			$in_diff = 1;
 		} elsif (m!^\+\+\+ ("?b/.+)!)  {
 			my $fn = $1;
 			$fn = (split('/', git_unquote($fn), 2))[1];
-			$seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
+			$seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
 			$in_diff = 1;
 		} elsif (/^--- (\S+)/) {
 			$in_diff = $1;
 			push @xnq, $_;
 		} elsif (defined $in_diff && /^\+\+\+ (\S+)/) {
-			$in_diff = $self->index_old_diff_fn(\%seen, $in_diff, $1,
-							$xnq);
+			$in_diff = index_old_diff_fn($self, \%seen, $in_diff,
+							$1, $xnq);
 		} elsif ($in_diff && s/^\+//) { # diff added
-			$self->index_diff_inc($_, 'XDFB', $xnq);
+			index_diff_inc($self, $_, 'XDFB', $xnq);
 		} elsif ($in_diff && s/^-//) { # diff removed
-			$self->index_diff_inc($_, 'XDFA', $xnq);
+			index_diff_inc($self, $_, 'XDFA', $xnq);
 		} elsif (m!^index ([a-f0-9]+)\.\.([a-f0-9]+)!) {
 			my ($ba, $bb) = ($1, $2);
 			index_git_blob_id($doc, 'XDFPRE', $ba);
@@ -244,7 +253,7 @@ sub index_diff ($$$) {
 			# traditional diff w/o -p
 		} elsif (/^@@ (?:\S+) (?:\S+) @@\s*(\S+.*)$/) {
 			# hunk header context
-			$self->index_diff_inc($1, 'XDFHH', $xnq);
+			index_diff_inc($self, $1, 'XDFHH', $xnq);
 		# ignore the following lines:
 		} elsif (/^(?:dis)similarity index/ ||
 				/^(?:old|new) mode/ ||
@@ -255,7 +264,9 @@ sub index_diff ($$$) {
 				/^Binary files .* differ/) {
 			push @xnq, $_;
 		} elsif ($_ eq '') {
-			$in_diff = undef;
+			# possible to be in diff context, some mail may be
+			# stripped by MUA or even GNU diff(1).  "git apply"
+			# treats a bare "\n" as diff context, too
 		} else {
 			push @xnq, $_;
 			warn "non-diff line: $_\n" if DEBUG && $_ ne '';
@@ -263,27 +274,42 @@ sub index_diff ($$$) {
 		}
 	}
 
-	$self->index_text(join("\n", @xnq), 1, 'XNQ');
+	index_text($self, join("\n", @xnq), 1, 'XNQ');
 }
 
 sub index_body ($$$) {
-	my ($self, $lines, $doc) = @_;
-	my $txt = join("\n", @$lines);
+	my ($self, $txt, $doc) = @_;
 	if ($doc) {
 		# does it look like a diff?
 		if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
-			$txt = undef;
-			$self->index_diff($lines, $doc);
+			index_diff($self, $txt, $doc);
 		} else {
-			$self->index_text($txt, 1, 'XNQ');
+			index_text($self, $txt, 1, 'XNQ');
 		}
 	} else {
-		$self->index_text($txt, 0, 'XQUOT');
+		index_text($self, $txt, 0, 'XQUOT');
+	}
+}
+
+sub index_xapian { # msg_iter callback
+	my ($part, $depth, @idx) = @{$_[0]};
+	my ($self, $doc) = @{$_[1]};
+	my $ct = $part->content_type || 'text/plain';
+	my $fn = $part->filename;
+	if (defined $fn && $fn ne '') {
+		index_text($self, $fn, 1, 'XFN');
 	}
-	@$lines = ();
+
+	my ($s, undef) = msg_part_text($part, $ct);
+	defined $s or return;
+
+	# split off quoted and unquoted blocks:
+	my @sections = split(/((?:^>[^\n]*\n)+)/sm, $s);
+	$part = $s = undef;
+	index_body($self, $_, /\A>/ ? 0 : $doc) for @sections;
 }
 
-sub add_xapian ($$$$$) {
+sub add_xapian ($$$$$$) {
 	my ($self, $mime, $num, $oid, $mids, $mid0) = @_;
 	my $smsg = PublicInbox::SearchMsg->new($mime);
 	my $doc = $X->{Document}->new;
@@ -295,46 +321,21 @@ sub add_xapian ($$$$$) {
 	my $dt = strftime('%Y%m%d%H%M%S', @ds);
 	add_val($doc, PublicInbox::Search::DT(), $dt);
 
-	my $tg = $self->term_generator;
+	my $tg = term_generator($self);
 
 	$tg->set_document($doc);
-	$self->index_text($subj, 1, 'S') if $subj;
-	$self->index_users($smsg);
-
-	msg_iter($mime, sub {
-		my ($part, $depth, @idx) = @{$_[0]};
-		my $ct = $part->content_type || 'text/plain';
-		my $fn = $part->filename;
-		if (defined $fn && $fn ne '') {
-			$self->index_text($fn, 1, 'XFN');
-		}
-
-		my ($s, undef) = msg_part_text($part, $ct);
-		defined $s or return;
-
-		my (@orig, @quot);
-		my @lines = split(/\n/, $s);
-		while (defined(my $l = shift @lines)) {
-			if ($l =~ /^>/) {
-				$self->index_body(\@orig, $doc) if @orig;
-				push @quot, $l;
-			} else {
-				$self->index_body(\@quot, 0) if @quot;
-				push @orig, $l;
-			}
-		}
-		$self->index_body(\@quot, 0) if @quot;
-		$self->index_body(\@orig, $doc) if @orig;
-	});
+	index_text($self, $subj, 1, 'S') if $subj;
+	index_users($self, $smsg);
 
+	msg_iter($mime, \&index_xapian, [ $self, $doc ]);
 	foreach my $mid (@$mids) {
-		$self->index_text($mid, 1, 'XM');
+		index_text($self, $mid, 1, 'XM');
 
 		# because too many Message-IDs are prefixed with
 		# "Pine.LNX."...
 		if ($mid =~ /\w{12,}/) {
 			my @long = ($mid =~ /(\w{3,}+)/g);
-			$self->index_text(join(' ', @long), 1, 'XM');
+			index_text($self, join(' ', @long), 1, 'XM');
 		}
 	}
 	$smsg->{to} = $smsg->{cc} = '';
@@ -355,18 +356,27 @@ sub add_xapian ($$$$$) {
 	$self->{xdb}->replace_document($num, $doc);
 }
 
+sub _msgmap_init ($) {
+	my ($self) = @_;
+	die "BUG: _msgmap_init is only for v1\n" if $self->{version} != 1;
+	$self->{mm} //= eval {
+		require PublicInbox::Msgmap;
+		PublicInbox::Msgmap->new($self->{inboxdir}, 1);
+	};
+}
+
 sub add_message {
 	# mime = Email::MIME object
 	my ($self, $mime, $bytes, $num, $oid, $mid0) = @_;
 	my $mids = mids_for_index($mime->header_obj);
-	$mid0 = $mids->[0] unless defined $mid0; # v1 compatibility
-	unless (defined $num) { # v1
-		$self->_msgmap_init;
-		$num = index_mm($self, $mime);
-	}
+	$mid0 //= $mids->[0]; # v1 compatibility
+	$num //= do { # v1
+		_msgmap_init($self);
+		index_mm($self, $mime);
+	};
 	eval {
 		if (need_xapian($self)) {
-			$self->add_xapian($mime, $num, $oid, $mids, $mid0)
+			add_xapian($self, $mime, $num, $oid, $mids, $mid0);
 		}
 		if (my $over = $self->{over}) {
 			$over->add_overview($mime, $bytes, $num, $oid, $mid0);
@@ -423,7 +433,7 @@ sub remove_message {
 		batch_do($self, 'Q' . $mid, sub {
 			my ($ids) = @_;
 			$db->delete_document($_) for @$ids;
-			$nr = scalar @$ids;
+			$nr += scalar @$ids;
 		});
 	};
 	if ($@) {
@@ -464,18 +474,6 @@ sub remove_by_oid {
 	scalar(@delete);
 }
 
-sub term_generator { # write-only
-	my ($self) = @_;
-
-	my $tg = $self->{term_generator};
-	return $tg if $tg;
-
-	$tg = $X->{TermGenerator}->new;
-	$tg->set_stemmer($self->stemmer);
-
-	$self->{term_generator} = $tg;
-}
-
 sub index_git_blob_id {
 	my ($doc, $pfx, $objid) = @_;
 
@@ -613,15 +611,6 @@ sub read_log {
 	$batch_cb->($nr, $latest, $newest);
 }
 
-sub _msgmap_init {
-	my ($self) = @_;
-	die "BUG: _msgmap_init is only for v1\n" if $self->{version} != 1;
-	$self->{mm} ||= eval {
-		require PublicInbox::Msgmap;
-		PublicInbox::Msgmap->new($self->{inboxdir}, 1);
-	};
-}
-
 sub _git_log {
 	my ($self, $opts, $range) = @_;
 	my $git = $self->{git};
@@ -677,7 +666,6 @@ sub is_ancestor ($$$) {
 	my $cmd = [ 'git', "--git-dir=$git->{git_dir}",
 		qw(merge-base --is-ancestor), $cur, $tip ];
 	my $pid = spawn($cmd);
-	defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!";
 	waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish';
 	$? == 0;
 }